Vehicle vibration monitoring method and device, vehicle and storage medium
By acquiring and processing the triaxial acceleration and angular velocity signals from the inertial measurement unit, the problems of false alarms and missed detections in vehicle vibration detection are solved, and accurate determination and effective identification of vehicle vibration are achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- BEI DOU ZHI LIAN KE JI YOU XIAN GONG SI
- Filing Date
- 2025-12-18
- Publication Date
- 2026-04-14
AI Technical Summary
Existing technologies for vehicle vibration detection are prone to false alarms and missed detections due to sensor noise, environmental vibration interference, and static offset, failing to effectively distinguish between minor disturbances and real impact events.
By acquiring the triaxial acceleration and triaxial angular velocity signals from the inertial measurement unit, the vector magnitude and magnitude change rate are calculated after data smoothing. The time-series integration and weighted fusion are then performed using a sliding window mechanism to generate target vibration metrics to determine valid vibration events.
It improves the ability to perceive complex vibration events, reduces false alarms, enhances the accurate identification of real vibration events, and reduces the risk of misjudgment caused by environmental disturbances.
Smart Images
Figure CN121855677A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of vehicle control technology, and in particular to a vehicle vibration monitoring method, device, vehicle, and storage medium. Background Technology
[0002] In vehicle sentry mode, vibration detection is a key mechanism for triggering DVR recording and remote alarms. Current technologies primarily rely on accelerometers in the inertial measurement unit (IMU) to collect triaxial acceleration data and make judgments based on fixed thresholds. While some solutions introduce simple filtering to suppress false triggers caused by signal abrupt changes, they are still limited to processing acceleration data in a single dimension. Because they do not adequately consider factors such as sensor noise, environmental vibration interference, and static offset, traditional methods are prone to frequent false alarms due to slight disturbances around the vehicle or sensor drift, resulting in users receiving numerous invalid alerts and potentially missing some well-hidden real impact events. Summary of the Invention
[0003] In view of this, embodiments of this application provide a vehicle vibration monitoring method, device, vehicle, and computer-readable storage medium, which can achieve accurate determination of vehicle vibration.
[0004] In a first aspect, embodiments of this application provide a vehicle vibration monitoring method, including: Acquire motion signals from each sensing channel; wherein the motion signals include a first motion signal representing linear motion and a second motion signal representing angular velocity; The magnitude of the acceleration vector and the rate of change of the magnitude of the acceleration vector are calculated based on the first motion signal, and the magnitude of the angular velocity vector and the rate of change of the magnitude of the angular velocity vector are calculated based on the second motion signal. A first preliminary vibration metric is generated based on the magnitude of the acceleration vector and the rate of change of the acceleration magnitude, and a second preliminary vibration metric is generated based on the magnitude of the angular velocity vector and the rate of change of the angular velocity magnitude. A sliding window mechanism is used to integrate the first preliminary vibration metric value and the second preliminary vibration metric value within the historical acquisition period to obtain the first smoothed vibration metric value and the second smoothed vibration metric value. The first smoothed vibration metric and the second smoothed vibration metric are fused together to obtain a target vibration metric, and a valid vibration event is determined based on the target vibration metric.
[0005] In an optional implementation, before calculating the magnitude of the acceleration vector and the rate of change of the magnitude of the acceleration vector based on the first motion signal, the method further includes: Data smoothing processing is performed on the signals of each axis in the first motion signal and the second motion signal to obtain the first corrected acceleration component and the first corrected angular velocity component; The step of calculating the magnitude of the acceleration vector and the rate of change of the magnitude of the acceleration vector based on the first motion signal, and calculating the magnitude of the angular velocity vector and the rate of change of the magnitude of the angular velocity vector based on the second motion signal, includes: The magnitude of the acceleration vector and the magnitude of the angular velocity vector are calculated based on the first corrected acceleration component and the first corrected angular velocity component, respectively. The rate of change of the acceleration magnitude is determined based on the magnitude of the acceleration vector at adjacent acquisition times, and the rate of change of the angular velocity magnitude is determined based on the magnitude of the angular velocity vector at adjacent acquisition times.
[0006] In an optional implementation, the first motion signal and the second motion signal are triaxial acceleration data signals and triaxial angular velocity signals acquired by an inertial measurement unit, respectively.
[0007] In an optional implementation, the data smoothing process performed on the signals of each axis in the first motion signal and the second motion signal includes: An independent state estimation model is established for each axial component in the first motion signal, and iterative filtering operations are performed based on the system dynamics equation and observation equation to output the first state estimate value of the corresponding axial component. An independent state estimation model is established for each axial component in the second motion signal, and iterative filtering operations are performed based on the system dynamics equations and observation equations to output the second state estimate value of the corresponding axial component.
[0008] In an optional implementation, generating a first preliminary vibration metric based on the magnitude of the acceleration vector and the rate of change of the magnitude of the acceleration includes: A first weight and a second weight are assigned to the magnitude of the acceleration vector and the rate of change of the magnitude of the acceleration, respectively; wherein the second weight is greater than the first weight. The first preliminary vibration metric value is obtained by adding the weighted acceleration vector magnitude to the weighted acceleration magnitude change rate. The process of generating a second preliminary vibration metric based on the angular velocity vector magnitude and the rate of change of the angular velocity magnitude includes: A third weight and a fourth weight are assigned to the magnitude of the angular velocity vector and the rate of change of the magnitude of the angular velocity vector, respectively; wherein the fourth weight is greater than the third weight. The second preliminary vibration metric is obtained by adding the weighted angular velocity vector magnitude to the weighted angular velocity magnitude change rate.
[0009] In an optional implementation, the step of using a sliding window mechanism to perform time-series integration of the first preliminary vibration metric value and the second preliminary vibration metric value within a historical acquisition period to obtain a first smoothed vibration metric value and a second smoothed vibration metric value includes: The average of the valid first preliminary vibration metric and the valid second preliminary vibration metric within the same sliding window is calculated respectively, and used as the first smooth vibration metric and the second smooth vibration metric respectively.
[0010] In an optional implementation, the step of fusing the first smoothed vibration metric value and the second smoothed vibration metric value to obtain the target vibration metric value includes: A fifth weight and a sixth weight are assigned to the first smooth vibration metric value and the second smooth vibration metric value, respectively; wherein the fifth weight is greater than the sixth weight. The weighted first smoothed vibration metric value is added to the weighted second smoothed vibration metric value to obtain the target vibration metric value.
[0011] Secondly, embodiments of this application provide a vehicle vibration monitoring device, comprising: An acquisition module is used to acquire motion signals from each sensing channel; wherein the motion signals include a first motion signal representing linear motion and a second motion signal representing angular velocity; The calculation module is used to calculate the magnitude of the acceleration vector and the rate of change of the magnitude of the acceleration vector based on the first motion signal, and to calculate the magnitude of the angular velocity vector and the rate of change of the magnitude of the angular velocity vector based on the second motion signal; The calculation module is also used to generate a first preliminary vibration metric value based on the magnitude of the acceleration vector and the rate of change of the magnitude of the acceleration vector, and to generate a second preliminary vibration metric value based on the magnitude of the angular velocity vector and the rate of change of the angular velocity vector. The integration module is used to perform time-series integration of the first preliminary vibration measurement value and the second preliminary vibration measurement value within the historical acquisition period using a sliding window mechanism to obtain the first smoothed vibration measurement value and the second smoothed vibration measurement value. The determination module is further configured to fuse the first smooth vibration metric value and the second smooth vibration metric value to obtain a target vibration metric value, and determine whether a valid vibration event has occurred based on the target vibration metric value.
[0012] Thirdly, embodiments of this application provide a vehicle, the vehicle including a processor and a memory, the memory storing a computer program, and the processor executing the computer program to implement the above-described vehicle vibration monitoring method.
[0013] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed on a processor, implements the vehicle vibration monitoring method described above.
[0014] The embodiments of this application have the following beneficial effects: By simultaneously acquiring two types of motion signals—linear motion and angular velocity—and extracting their vector magnitude and rate of change of magnitude respectively, this application can more comprehensively characterize the dynamic characteristics of vibrations experienced by a vehicle. Compared to traditional methods that rely solely on a single acceleration signal, this application fully utilizes the characteristics of multi-dimensional inertial data, effectively improving the ability to perceive complex vibration events. By generating preliminary vibration metrics for both acceleration and angular velocity channels and integrating them temporally using a sliding window mechanism, the stability and continuity of the data can be enhanced, suppressing the risk of misjudgment caused by instantaneous noise interference. Finally, the smoothed dual-channel vibration information is fused into a unified target vibration metric, enabling accurate determination of whether a valid vibration event has occurred. This application can effectively reduce false alarms caused by environmental disturbances. Attached Figure Description
[0015] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.
[0016] Figure 1 A first flowchart of a vehicle vibration monitoring method according to an embodiment of this application is shown; Figure 2 A second flowchart of the vehicle vibration monitoring method according to an embodiment of this application is shown; Figure 3 A schematic diagram of the third process of the vehicle vibration monitoring method according to an embodiment of this application is shown; Figure 4 A schematic diagram of a vehicle vibration monitoring device according to an embodiment of this application is shown. Detailed Implementation
[0017] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.
[0018] The components of the embodiments of this application described and illustrated in the accompanying drawings can be arranged and designed in a variety of different configurations. Therefore, the following detailed description of the embodiments of this application provided in the drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.
[0019] In the following text, the terms "comprising," "having," and their cognates, which may be used in various embodiments of this application, are intended only to indicate a particular feature, number, step, operation, element, component, or combination thereof, and should not be construed as primarily excluding the presence of one or more other features, numbers, steps, operations, elements, components, or combinations thereof, or adding the possibility of one or more combinations thereof. Furthermore, the terms "first," "second," "third," etc., are used only for distinguishing descriptions and should not be construed as indicating or implying relative importance.
[0020] Unless otherwise specified, all terms used herein (including technical and scientific terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which the various embodiments of this application pertain. Terms (such as those defined in commonly used dictionaries) shall be interpreted as having the same meaning as in their contextual meaning in the relevant technical field and shall not be construed as having an idealized or overly formal meaning, unless clearly defined in the various embodiments of this application.
[0021] The following detailed description of some embodiments of this application is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.
[0022] The following examples illustrate the vehicle vibration monitoring method.
[0023] Figure 1 A schematic flowchart of a vehicle vibration monitoring method according to an embodiment of this application is shown. Exemplarily, the vehicle vibration monitoring method includes steps S100-S400: Step S100: Acquire motion signals from each sensor channel.
[0024] The first motion signal and the second motion signal are the triaxial acceleration data signal and the triaxial angular velocity signal obtained by the inertial measurement unit, respectively.
[0025] In this embodiment, raw data from vehicle sensors is first acquired. These sensors constitute multiple independent sensing channels for sensing different physical motion states of the vehicle. The motion signals include at least a first motion signal representing linear motion and a second motion signal representing angular velocity.
[0026] The first motion signal, representing linear motion, directly reflects the acceleration changes of the vehicle as a whole along the X, Y, and Z axes in three-dimensional space. This first motion signal can be understood as triaxial acceleration data signals acquired in real time by an inertial measurement unit (IMU) installed on the vehicle. This IMU continuously outputs... , The three data components represent the magnitude of the vehicle's instantaneous acceleration in the corresponding direction. A second motion signal, representing angular velocity, reflects the rate at which the vehicle rotates about its own X, Y, and Z axes. Similarly, the second motion signal can be a three-axis angular velocity signal acquired in real time by the same inertial measurement unit (IMU). This IMU also outputs... , The data consists of three components, the values of which represent the instantaneous angular velocity of the vehicle around the corresponding axis.
[0027] Specifically, the system can periodically read the aforementioned six-dimensional data (three-axis acceleration and three-axis angular velocity) from the inertial measurement unit at a fixed sampling frequency (e.g., 50Hz or 100Hz), forming a complete snapshot of the motion state at each moment k. These raw... , , , The data serves as the foundation for subsequent processing. Due to noise and environmental interference inherent in the sensors themselves, these raw signals may contain glitches and random fluctuations, and therefore cannot be directly used to determine whether a valid vibration event has occurred in the vehicle. Thus, data smoothing processing is necessary.
[0028] Step S200: Calculate the magnitude of the acceleration vector and the rate of change of the magnitude of the acceleration vector based on the first motion signal, and calculate the magnitude of the angular velocity vector and the rate of change of the magnitude of the angular velocity vector based on the second motion signal.
[0029] As an example, after acquiring the raw triaxial acceleration and triaxial angular velocity data signals, in order to accurately detect vehicle vibration, it is necessary to extract key features that characterize the severity of vibration from these multidimensional data. However, directly using the raw signals for feature extraction is severely affected by adverse factors such as sensor noise, zero-bias drift, temperature effects, and external electromagnetic interference, leading to an increased false trigger rate. Therefore, before performing subsequent feature calculations, each axial component of the first motion signal (triaxial acceleration) and the second motion signal (triaxial angular velocity) must be independently smoothed to obtain more stable and reliable first corrected acceleration and first corrected angular velocity components.
[0030] like Figure 2 As shown, data smoothing processing is performed on the signals of each axis in the first motion signal and the second motion signal, including steps S210-S220: Step S210: Establish an independent state estimation model for each axial component in the first motion signal, and perform iterative filtering operations based on the system dynamics equation and observation equation to output the first state estimate value of the corresponding axial component.
[0031] The state estimation model can employ a Kalman filter, whose core function is to perform optimal state estimation on the noisy raw sensor measurement data, thereby achieving effective denoising and smoothing of the acceleration signal. Based on the minimum mean square error criterion, this method dynamically fuses predicted information with measured data in the time domain, significantly suppressing high-frequency random noise and transient interference while preserving true vibration characteristics.
[0032] Specifically, for each component of the triaxial acceleration data signal output by the inertial measurement unit (IMU) , The system constructs an independently operating standard Kalman filter model for each axis. This design of independent modeling for each axis in this embodiment avoids signal coupling between different spatial directions, thereby improving the flexibility and adaptability of the filtering process for each channel.
[0033] With X-axis acceleration components For example, its corresponding Kalman filter abstracts the motion state at the current moment into a two-dimensional state variable. ;in, This represents the virtual displacement obtained by integrating historical acceleration at the k-th sampling time, reflecting the position trend; The equivalent velocity term at that moment describes the trend of acceleration. Although acceleration itself is a direct measurement, introducing this state model can effectively separate real dynamic changes from random noise.
[0034] The state evolution of the system follows a linear dynamic model, and its state transition equation is: ,in, It is a prediction of the current state based on information from the previous moment. The state transition matrix is F = ;in, This represents the time interval between two consecutive samples, determined by the IMU's sampling frequency. For example, when the sampling frequency is 50Hz, The value is 0.02s. This state transition matrix reflects the fundamental physical laws under the assumption of uniform acceleration, namely, that displacement increases linearly with velocity, while velocity remains relatively stable in the absence of sudden external forces.
[0035] In order to incorporate actual measurements into the estimation process, the system sets up observation equations. ,in, H is the raw X-axis acceleration value collected at the current moment; The observation matrix represents only the velocity terms in the state variables. Directly corresponds to acceleration measurement; The measurement noise is assumed to follow a zero-mean Gaussian distribution, and its statistical properties are determined by the measurement noise covariance. describe.
[0036] In addition, the system also introduces the process noise covariance matrix. It is used to characterize the modeling uncertainty and the impact of external uncontrollable disturbances. The value is determined based on the IMU device datasheet and in conjunction with actual vehicle calibration experiments, and its range can be... Its value can be adjusted according to the specific sensor model and installation environment.
[0037] During the algorithm startup phase, the filters need to be initialized. For the X-axis and Y-axis acceleration channels, assuming the vehicle is initially stationary with no obvious displacement trend, the initial state estimates are set as follows: , Accordingly, the initial error covariance matrix is set to an appropriate positive value to reflect the initial uncertainty.
[0038] However, for the Z-axis acceleration component Since a vehicle is primarily affected by Earth's gravitational acceleration when stationary, its theoretical baseline value is approximately 9.8. If its initial value is still set to zero, the filter will exhibit a large deviation in the initial startup phase and require a long time to converge to the correct level. Therefore, in this embodiment, physical prior compensation is specifically applied to the Z-axis filter: its initial velocity term is set to 9.8.
[0039] Furthermore, within each sampling period, the system sequentially executes the following two core phases: The first stage is the prediction stage. In this stage, the filter infers the current state based on the optimal estimate from the previous time step and the system dynamics model.
[0040] State prediction:
[0041] Error covariance prediction: =F
[0042] in, It represents the degree of uncertainty in the predicted state and reflects the system's level of confidence in the future state.
[0043] Then, the update phase begins, where the prediction results are corrected using the actual measurements at the current moment.
[0044] First, calculate the Kalman gain, i.e. The Kalman gain Adaptively balance the reliability of predicted and measured values: when measurement noise is low, the gain is high and more reliance is placed on measured data; conversely, when measurement noise is high, more trust is placed on model predictions.
[0045] Then update the state estimate, i.e. This update process can output the optimal state estimate at the current moment.
[0046] Finally, update the error covariance, i.e. This step can reduce estimation uncertainty.
[0047] Finally, from the updated state vector Extracting the velocity term This value serves as the first state estimate for that axis. This value is the optimal estimate of the X-axis acceleration obtained after Kalman filtering, exhibiting a high signal-to-noise ratio and stronger anti-interference capability.
[0048] Similarly, independent Kalman filter models are constructed for the Y-axis and Z-axis acceleration components, and prediction and update operations are performed according to the same process to output the corresponding state estimates.
[0049] It is understandable that the above method can achieve channel-by-channel fine filtering of the triaxial acceleration signal. This method can not only effectively suppress the influence of high-frequency noise and transient glitches, but also achieve rapid response to real vehicle vibration events.
[0050] Step S220: Establish an independent state estimation model for each axial component in the second motion signal, and perform iterative filtering operations based on the system dynamics equations and observation equations to output the second state estimation value of the corresponding axial component.
[0051] It is understandable that the process of obtaining the second state estimate is the same as that of obtaining the first state estimate, and will not be repeated here.
[0052] In some implementations, such as Figure 3 As shown, step S200 includes steps S230-S240: Step S230: Calculate the magnitude of the acceleration vector and the magnitude of the angular velocity vector based on the first corrected acceleration component and the first corrected angular velocity component, respectively.
[0053] Exemplary, in obtaining the first corrected acceleration component Then, the system calculates the composite value of the acceleration vector at the current time k, that is, the magnitude of the acceleration vector. The formula for calculating the magnitude of the acceleration vector is: = The magnitude of this acceleration vector represents the total intensity of the linear acceleration of the vehicle in three-dimensional space. Similarly, after obtaining the first corrected angular velocity component... Then, the system calculates the magnitude of the angular velocity vector at the current time k. The calculation formula is as follows: = The magnitude of this angular velocity vector represents the overall rotational speed of the vehicle.
[0054] Step S240: Determine the rate of change of acceleration magnitude based on the magnitude of acceleration vector at adjacent acquisition times, and determine the rate of change of angular velocity magnitude based on the magnitude of angular velocity vector at adjacent acquisition times.
[0055] As an example, relying solely on the absolute value of the vector magnitude is ineffective in distinguishing between slow environmental disturbances (such as rustling grass) and sudden, violent impacts (such as collisions). Therefore, in this embodiment, to capture vibrations, i.e., rapid changes in physical quantities, the rate of change of the magnitude needs to be further calculated. Specifically, the rate of change of the acceleration magnitude... It is achieved by calculating the magnitude of the acceleration vector at the current acquisition time k. Compared with the previous collection time Magnitude of acceleration vector The difference is obtained by dividing by the sampling time interval Δt, i.e. Similarly, the rate of change of the modulus of angular velocity The calculation formula is: The calculated rates of change of acceleration modulus and angular velocity modulus reflect how quickly the combined intensity of acceleration or angular velocity changes over time; the larger the values, the more intense the motion experienced by the vehicle. This embodiment effectively suppresses low-frequency, slowly changing noise interference through the rates of change of acceleration modulus and angular velocity modulus, while maintaining high sensitivity to high-frequency, sudden impact events.
[0056] Step S300: Generate a first preliminary vibration metric value based on the magnitude of the acceleration vector and the rate of change of the magnitude of the acceleration vector, and generate a second preliminary vibration metric value based on the magnitude of the angular velocity vector and the rate of change of the magnitude of the angular velocity vector.
[0057] In some implementations, generating a first preliminary vibration metric based on the magnitude of the acceleration vector and the rate of change of the acceleration magnitude includes: assigning a first weight and a second weight to the magnitude of the acceleration vector and the rate of change of the acceleration magnitude, respectively; wherein the second weight is greater than the first weight; and adding the weighted magnitude of the acceleration vector to the weighted rate of change of the acceleration magnitude to obtain the first preliminary vibration metric.
[0058] The second preliminary vibration metric is generated based on the angular velocity vector magnitude and the rate of change of the angular velocity vector magnitude, including: assigning a third weight and a fourth weight to the angular velocity vector magnitude and the rate of change of the angular velocity vector magnitude, respectively; wherein the fourth weight is greater than the third weight; and adding the weighted angular velocity vector magnitude and the weighted rate of change of the angular velocity vector magnitude to obtain the second preliminary vibration metric.
[0059] Specifically, after feature extraction is completed and the magnitude of the acceleration vector is obtained... , rate of change of acceleration modulus angular velocity vector magnitude and angular velocity modulus change rate Next, this embodiment needs to synthesize these features into an index that can quantify the probability of vibration events. During the fusion process, this embodiment uses a weighted fusion method to generate a preliminary vibration assessment result for each sensor dimension.
[0060] First, regarding acceleration motion information, based on the magnitude of the acceleration vector... and the rate of change of acceleration modulus Generate the first preliminary vibration measurement value Furthermore, since effective vibration events of a vehicle (such as collisions and scrapes) typically manifest as instantaneous, severe impacts, their most significant characteristic is the abrupt change in physical quantities, i.e., a high rate of change. The absolute value of the magnitude alone may be affected by the vehicle's static posture or slow swaying, contributing relatively little to the judgment of sudden events. Therefore, in this embodiment, a weighted summation method can be used to calculate the first preliminary vibration metric value. Specifically, these are the magnitudes of the acceleration vector. Assign a first weight and the rate of change of acceleration modulus Assign a second weight To highlight the importance of dynamic changes, a second weight is set. Greater than the first weight (For example, It can be 0.7. (It can be 0.3). Then, the two weighted terms are added together to obtain the first preliminary vibration metric value, i.e., the first preliminary vibration metric value. .
[0061] Similarly, for rotational motion information, the system is based on the magnitude of the angular velocity vector. and angular velocity modulus change rate Generate a second preliminary vibration metric. Certain abnormal vehicle conditions (such as being dragged or overturned) are accompanied by noticeable rotational motion. Similar to acceleration signals, abrupt changes in rotation (i.e., the rate of change of angular velocity) are a better indicator of vehicle vibration than its sustained intensity. Therefore, when determining the second preliminary vibration metric, the magnitudes of the angular velocity vectors are used. Assign a third weight and the rate of change of angular velocity modulus Assign a fourth weight Similarly, to emphasize the instantaneous impact, a fourth weight is established. Greater than the third weight (For example, It can be 0.7. (It can be 0.3). Adding the two weighted terms together yields the second preliminary vibration metric value, i.e., the second preliminary vibration metric value. .
[0062] Therefore, through step S300, this embodiment integrates the multidimensional features of each sensor dimension into a one-dimensional preliminary vibration measurement value with physical meaning. and These two values together form the basis for subsequent time-domain integration and cross-sensor fusion.
[0063] Step S400: The sliding window mechanism is used to integrate the first preliminary vibration measurement value and the second preliminary vibration measurement value within the historical acquisition period to obtain the first smooth vibration measurement value and the second smooth vibration measurement value.
[0064] Specifically, this step involves calculating the average of the effective first preliminary vibration metric and the effective second preliminary vibration metric within the same sliding window, which are then used as the first smoothed vibration metric and the second smoothed vibration metric, respectively.
[0065] As an example, the first preliminary vibration measurement value at each moment was obtained in the manner described above. Second preliminary vibration measurement value Subsequently, directly using the instantaneous value of a single point for decision-making may be affected by accidental noise pulses or brief interference, leading to unstable judgments. To improve the reliability of the detection results, this embodiment introduces a sliding window mechanism to integrate historical data over a period of time to smooth out random fluctuations and thus obtain a relatively stable vibration level.
[0066] Specifically, this embodiment is and Maintain a fixed-length sliding window, which stores the values calculated within the most recent N consecutive sampling periods. and Numerical values. The window length N can be set according to the typical noise level of the vehicle parking environment, for example, it can be set to 10 sampling periods (if the sampling frequency is 50Hz, it corresponds to about 0.2 seconds of historical data). It is understood that the number of sampling periods within the sliding window is only an example, and can be adjusted within a reasonable range according to the actual test results.
[0067] At the arrival of each new sampling period k, the system performs a timing integration operation. First, the timing calculation for the current period is... and The new data is stored in each of the respective sliding windows. Before storing, you can... and Validity screening can be performed by pre-setting a reasonable threshold range to determine whether new data is an outlier (e.g., extreme spikes caused by electromagnetic interference). If new data is identified as an outlier, it is discarded and not included in the window calculation; otherwise, it is stored in the window, and the oldest data point in the window is removed at the same time, so as to ensure that the window always contains only the latest N valid data.
[0068] After the data update is complete, calculate the arithmetic mean of all valid data points within each of the two sliding windows. The calculated average is the first smoothed vibration metric after time-domain smoothing. Second smooth vibration metric .
[0069] It is understood that this embodiment, through the timing integration in step S400, transforms the instantaneous and potentially fluctuating preliminary vibration measurement value into a smoother and more stable evaluation index that better represents the recent overall vibration trend, so as to make the subsequent judgment on vehicle vibration more accurate.
[0070] Step S500: The first smooth vibration metric value and the second smooth vibration metric value are fused to obtain the target vibration metric value, and it is determined whether a valid vibration event has occurred based on the target vibration metric value.
[0071] In this step, the first smooth vibration metric value and the second smooth vibration metric value are fused to obtain the target vibration metric value. This includes: assigning a fifth weight and a sixth weight to the first smooth vibration metric value and the second smooth vibration metric value respectively; wherein the fifth weight is greater than the sixth weight; and adding the weighted first smooth vibration metric value and the weighted second smooth vibration metric value to obtain the target vibration metric value.
[0072] As an example, after obtaining the first and second smoothed vibration metrics that have undergone time-domain smoothing, this embodiment requires a final comprehensive judgment of the two evaluation results from the accelerometer and gyroscope, respectively, to arrive at a unified vehicle vibration risk level.
[0073] Specifically, since in most abnormal vehicle scenarios (such as collisions or scrapes), the main energy manifests as linear impact force, the first smoothed vibration metric obtained from accelerometer data should dominate the final judgment. The second smoothed vibration metric obtained from gyroscope data serves as important supplementary information, used to detect special events that may be accompanied by significant rotational components (such as when a vehicle is towed). To reflect this hierarchy and make vibration judgment more accurate, this embodiment assigns a fifth weight to each of the first smoothed vibration metrics. And assign a sixth weight to the second smooth vibration metric. Among them, the fifth weight is greater than the sixth weight (for example, It can be 0.7. (The value can be 0.3). By adding the two weighted terms, the target vibration measurement value can be obtained. Its calculation formula can be expressed as: .
[0074] This embodiment achieves complementary advantages of multi-source information in this way, ensuring high sensitivity to linear impacts while also taking into account the detection capability of rotational anomalies, thereby improving the overall accuracy and reliability of the judgment.
[0075] Furthermore, in obtaining the target vibration measurement value Next, this implementation compares the measured vibration value with a preset threshold. This preset threshold is a critical value calibrated based on extensive real-vehicle testing, effectively distinguishing between normal environmental disturbances and genuine threatening vibrations. Specifically, if the target vibration metric is greater than the preset threshold, a valid vehicle vibration event is determined to have occurred; otherwise, no valid vibration event is determined to have occurred. When a valid vibration event is determined to have occurred, the system immediately triggers the corresponding security response mechanism, such as activating the in-vehicle DVR (digital video recorder) to start recording video of the surrounding environment and pushing an alarm notification to the vehicle owner's mobile client via the vehicle networking module, reminding the owner to check in time.
[0076] This embodiment employs a multi-channel independent state estimation model to perform refined filtering on the triaxial acceleration and triaxial angular velocity signals, effectively suppressing the effects of sensor noise, zero-bias drift, and external environmental interference, significantly improving the signal-to-noise ratio of the original motion signal. Building upon this, the embodiment constructs dynamic vibration features by combining the magnitudes and rates of change of the acceleration and angular velocity vectors, and adopts a hierarchical weighted fusion mechanism to highlight the dominant role of the rate of change in identifying sudden impact events. This makes the system more sensitive and responsive to threatening vibrations such as real collisions and scratches. Simultaneously, by introducing a sliding window to integrate historical vibration metrics over time, and combining this with an effectiveness screening strategy to eliminate instantaneous anomalies, the stability and reliability of the detection results are further enhanced, avoiding false triggers caused by single-frame glitches or brief disturbances. Finally, through weighted fusion decision-making of the acceleration and angular velocity channels, while ensuring a high detection rate for linear impacts, the system also considers the ability to identify rotational anomalies, thereby achieving multi-dimensional information complementarity and accurately determining vehicle vibration events.
[0077] Figure 4 A schematic diagram of a vehicle vibration monitoring device according to an embodiment of this application is shown. Exemplarily, the vehicle vibration monitoring device includes: The acquisition module 100 is used to acquire motion signals from each sensing channel; wherein the motion signals include a first motion signal representing linear motion and a second motion signal representing angular velocity.
[0078] The calculation module 200 is used to calculate the magnitude of the acceleration vector and the rate of change of the magnitude of the acceleration vector based on the first motion signal, and to calculate the magnitude of the angular velocity vector and the rate of change of the magnitude of the angular velocity vector based on the second motion signal.
[0079] The calculation module 200 is also used to generate a first preliminary vibration metric based on the magnitude of the acceleration vector and the rate of change of the magnitude of the acceleration vector, and to generate a second preliminary vibration metric based on the magnitude of the angular velocity vector and the rate of change of the angular velocity vector.
[0080] The integration module 300 is used to perform time-series integration of the first preliminary vibration measurement value and the second preliminary vibration measurement value within the historical acquisition period using a sliding window mechanism to obtain the first smooth vibration measurement value and the second smooth vibration measurement value.
[0081] The determination module 400 is further configured to fuse the first smooth vibration metric value and the second smooth vibration metric value to obtain a target vibration metric value, and determine whether a valid vibration event has occurred based on the target vibration metric value.
[0082] It is understood that the device in this embodiment corresponds to the vehicle vibration monitoring method in the above embodiment, and the options in the above embodiment are also applicable to this embodiment, so they will not be described again here.
[0083] This application also provides a vehicle, exemplary in that the vehicle includes a processor and a memory, wherein the memory stores a computer program, and the processor, by running the computer program, causes the vehicle to perform the functions of the various modules in the above-described vehicle vibration monitoring method or vehicle vibration monitoring device.
[0084] The processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, including at least one of a Central Processing Unit (CPU), Graphics Processing Unit (GPU), Network Processor (NP), Digital Signal Processor (DSP), Application-Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor can be a microprocessor or any conventional processor, capable of implementing or executing the methods, steps, and logic block diagrams disclosed in the embodiments of this application.
[0085] The memory can be, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), etc. The memory is used to store computer programs, and the processor can execute the computer programs accordingly after receiving execution instructions.
[0086] This application also provides a computer-readable storage medium for storing the computer program used in the aforementioned vehicle. For example, the computer-readable storage medium may include, but is not limited to, various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.
[0087] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that, in alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.
[0088] In addition, the functional modules or units in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.
[0089] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a smartphone, personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application.
[0090] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.
Claims
1. A method for monitoring vehicle vibration, characterized in that, include: Acquire motion signals from each sensing channel; wherein the motion signals include a first motion signal representing linear motion and a second motion signal representing angular velocity; The magnitude of the acceleration vector and the rate of change of the magnitude of the acceleration vector are calculated based on the first motion signal, and the magnitude of the angular velocity vector and the rate of change of the magnitude of the angular velocity vector are calculated based on the second motion signal. A first preliminary vibration metric is generated based on the magnitude of the acceleration vector and the rate of change of the acceleration magnitude, and a second preliminary vibration metric is generated based on the magnitude of the angular velocity vector and the rate of change of the angular velocity magnitude. A sliding window mechanism is used to integrate the first preliminary vibration metric value and the second preliminary vibration metric value within the historical acquisition period to obtain the first smoothed vibration metric value and the second smoothed vibration metric value. The first smoothed vibration metric and the second smoothed vibration metric are fused together to obtain a target vibration metric, and a valid vibration event is determined based on the target vibration metric.
2. The vehicle vibration monitoring method according to claim 1, characterized in that, Before calculating the magnitude of the acceleration vector and the rate of change of the magnitude of the acceleration vector based on the first motion signal, the method further includes: Data smoothing processing is performed on the signals of each axis in the first motion signal and the second motion signal to obtain the first corrected acceleration component and the first corrected angular velocity component; The step of calculating the magnitude of the acceleration vector and the rate of change of the magnitude of the acceleration vector based on the first motion signal, and calculating the magnitude of the angular velocity vector and the rate of change of the magnitude of the angular velocity vector based on the second motion signal, includes: The magnitude of the acceleration vector and the magnitude of the angular velocity vector are calculated based on the first corrected acceleration component and the first corrected angular velocity component, respectively. The rate of change of the acceleration magnitude is determined based on the magnitude of the acceleration vector at adjacent acquisition times, and the rate of change of the angular velocity magnitude is determined based on the magnitude of the angular velocity vector at adjacent acquisition times.
3. The vehicle vibration monitoring method according to claim 2, characterized in that, The first motion signal and the second motion signal are triaxial acceleration data signal and triaxial angular velocity signal acquired by the inertial measurement unit, respectively.
4. The vehicle vibration monitoring method according to claim 2, characterized in that, The step of performing data smoothing processing on the signals of each axis in the first motion signal and the second motion signal includes: An independent state estimation model is established for each axial component in the first motion signal, and iterative filtering operations are performed based on the system dynamics equation and observation equation to output the first state estimate value of the corresponding axial component. An independent state estimation model is established for each axial component in the second motion signal, and iterative filtering operations are performed based on the system dynamics equations and observation equations to output the second state estimate value of the corresponding axial component.
5. The vehicle vibration monitoring method according to claim 1, characterized in that, The process of generating a first preliminary vibration metric based on the magnitude of the acceleration vector and the rate of change of the magnitude of the acceleration includes: A first weight and a second weight are assigned to the magnitude of the acceleration vector and the rate of change of the magnitude of the acceleration, respectively; wherein the second weight is greater than the first weight. The first preliminary vibration metric value is obtained by adding the weighted acceleration vector magnitude to the weighted acceleration magnitude change rate. The process of generating a second preliminary vibration metric based on the angular velocity vector magnitude and the rate of change of the angular velocity magnitude includes: A third weight and a fourth weight are assigned to the magnitude of the angular velocity vector and the rate of change of the magnitude of the angular velocity vector, respectively; wherein the fourth weight is greater than the third weight. The second preliminary vibration metric is obtained by adding the weighted angular velocity vector magnitude to the weighted angular velocity magnitude change rate.
6. The vehicle vibration monitoring method according to claim 1, characterized in that, The step of using a sliding window mechanism to integrate the first preliminary vibration metric value and the second preliminary vibration metric value within the historical acquisition period to obtain the first smoothed vibration metric value and the second smoothed vibration metric value includes: The average of the valid first preliminary vibration metric and the valid second preliminary vibration metric within the same sliding window is calculated respectively, and used as the first smooth vibration metric and the second smooth vibration metric respectively.
7. The vehicle vibration monitoring method according to claim 1, characterized in that, The step of fusing the first smoothed vibration metric value and the second smoothed vibration metric value to obtain the target vibration metric value includes: A fifth weight and a sixth weight are assigned to the first smooth vibration metric value and the second smooth vibration metric value, respectively; wherein the fifth weight is greater than the sixth weight. The weighted first smoothed vibration metric value is added to the weighted second smoothed vibration metric value to obtain the target vibration metric value.
8. A vehicle vibration monitoring device, characterized in that, include: An acquisition module is used to acquire motion signals from each sensing channel; wherein the motion signals include a first motion signal representing linear motion and a second motion signal representing angular velocity; The calculation module is used to calculate the magnitude of the acceleration vector and the rate of change of the magnitude of the acceleration vector based on the first motion signal, and to calculate the magnitude of the angular velocity vector and the rate of change of the magnitude of the angular velocity vector based on the second motion signal; The calculation module is also used to generate a first preliminary vibration metric value based on the magnitude of the acceleration vector and the rate of change of the magnitude of the acceleration vector, and to generate a second preliminary vibration metric value based on the magnitude of the angular velocity vector and the rate of change of the angular velocity vector. The integration module is used to perform time-series integration of the first preliminary vibration measurement value and the second preliminary vibration measurement value within the historical acquisition period using a sliding window mechanism to obtain the first smoothed vibration measurement value and the second smoothed vibration measurement value. The determination module is further configured to fuse the first smooth vibration metric value and the second smooth vibration metric value to obtain a target vibration metric value, and determine whether a valid vibration event has occurred based on the target vibration metric value.
9. A vehicle, characterized in that, The vehicle includes a processor and a memory, the memory storing a computer program, and the processor executing the computer program to implement the vehicle vibration monitoring method according to any one of claims 1-7.
10. A computer-readable storage medium, characterized in that, It stores a computer program, which, when executed on a processor, implements the vehicle vibration monitoring method according to any one of claims 1-7.